Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description is free to add the operationally important part: the exact four result states (pending/approved/denied/expired) in a tool with no output schema, plus the downstream constraint that execute_swap only works until the session ends. What is missing is timing behavior — how long 'expired' takes, whether polling is expected, and whether the code is single-use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The core question and its possible outcomes are front-loaded, and the second sentence carries the one piece of follow-on context the agent actually needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only poller with no output schema, enumerating the return states and the approval gate is the essential content, and both are present. The remaining gap is that the 'code' parameter's origin is undocumented, which for a 0%-coverage schema is a real (if small) hole.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter 'code' has 0% schema description coverage — only a regex pattern — and the description never mentions it, so nothing explains that it is the request code returned by request_session. The agent must infer the parameter's origin and format from the sibling tool name, which the description does not compensate for.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Whether the person has answered a request_session" states the resource (a session request) and the question being answered, and the sibling request_session is named explicitly so the pairing is unmistakable. It is clear without the input schema, though the verb is implicit (no "check" / "poll") rather than stated outright.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: by naming request_session the description suggests this is called after creating a request to check for an answer, and the second sentence routes the agent onward to execute_swap once approved. There is no explicit when-to-use statement, no guidance on polling/retry cadence, and no mention of which sibling (e.g. swap_status) to use once approved versus while pending.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.